datasets

alignement.py

@@ -183,14 +183,14 @@ def compare_include_df(df, sub_df, save = True, path = 'temp.png'):
 # dataset_train.to_pickle('database/data_DIA_ISA_55_test.pkl')
 
 # data_train_1 = pd.read_pickle('database/data_DIA_ISA_55_test_30_01.pkl').reset_index(drop=True)
-# data_train_2 = pd.read_pickle('database/data_DIA_ISA_55_train_30_01.pkl').reset_index(drop=True)
-# data_ori = pd.read_csv('database/data_train.csv').reset_index(drop=True)
-# data_ori['Sequence']=data_ori['sequence']
-# data_ori['Retention time']=data_ori['irt']
+data_train_2 = pd.read_pickle('database/data_DIA_ISA_55_train_30_01.pkl').reset_index(drop=True)
+data_ori = pd.read_csv('database/data_train.csv').reset_index(drop=True)
+data_ori['Sequence']=data_ori['sequence']
+data_ori['Retention time']=data_ori['irt']
 # data_train = pd.concat([data_train_2,data_train_1]).reset_index(drop=True)
-# data_align = align(data_train, data_ori)
-#
-# data_align.to_pickle('database/data_ISA_dual_align.pkl')
+data_align = align(data_train_2, data_ori)
+
+data_align.to_pickle('database/data_ISA_dual_align_train.pkl')
 
 
 #compare DIANN pred to DIA mesures
@@ -211,7 +211,7 @@ def compare_include_df(df, sub_df, save = True, path = 'temp.png'):
 
 
 # create augmented dataset from ISA data + column invariant prosit peptides
-df_base = pd.read_pickle('database/data_DIA_ISA_55_train_30_01.pkl')
+df_base = pd.read_pickle('database/data_ISA_dual_align_train.pkl')
 df_base = df_base[['Sequence','Retention time']]
 
 df_1 = pd.read_pickle('database/data_prosit_threshold_1.pkl')